Loopback bidirectional Anthropic/OpenAI API proxy with tool-call validation and multi-provider routing.

looprun core: the AgentSpec governance layer for LLM agents — typed deterministic guards (prose+check pairing), the byte-stable scoped assembledPrompt renderer, and the backend-agnostic governed-turn machine. Framework-free: zero runtime dependencies; bac

Used to ensure modern CLI scripts fail silently on old js versions. Useful for static analysis tools and similar

micromark extension to support math (`$C_L$`, `\(C_L\)`)

Detox driver for Wix Pilot usage

[llm-ui](https://llm-ui.com) JSON blocks for building custom components.

Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget

[llm-ui](https://llm-ui.com) code block.

OCI NodeJS client for Cloud Guard Service

OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more

Navigation Guard for Next.js App Router and Pages Router.

A Vite plugin that lets SPA applications generate a Content Security Policy (CSP).

A library for working with LLMs in Grafana plugins

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

A drop-in spend cap and audit log for LLM API calls

Website URL discovery + LLM page selection — scouts a site for the pages worth reading (seeds support-bot knowledge bases).

Automated Test-Driven Development enforcement for Claude Code

[](https://dl.circleci.com/status-badge/redirect/gh/taneliang/coerce-llm-output/tree/main) [![codecov](https://codecov.io/github/taneliang/coerce-l

Universal library for evaluating AI models

The best library to work with LLMs